[Support]: Frigate + Hail 8 is compiled as Hailo 8L

[ParalaXEngineering]

Checklist

• I have updated to the latest available Frigate version.
• I have cleared the cache of my browser.
• I have tried a different browser to see if it is related to my browser.
• I have tried reproducing the issue in incognito mode to rule out problems with any third party extensions or plugins I have installed.
• I have asked the AI at https://docs.frigate.video about my issue.

Describe the problem you are having

Hi,

It seems that in frigate +, when asking to compile a new model for Hailo8, it creates an Hailo8L model. The first time it happened I thought I had mis-clicked, but this second time I had the same results.

Steps to reproduce

1. Ask for a model in Frigate + with Hailo8 as detector
2. The model is compiled in Hailo8L

Version

16.2

In which browser(s) are you experiencing the issue with?

No response

Frigate config file

-

docker-compose file or Docker CLI command

-

Relevant Frigate log output

-

Relevant go2rtc log output

-

Operating system

Home Assistant OS

Install method

Home Assistant Add-on

Network connection

Wired

Camera make and model

Screenshots of the Frigate UI's System metrics pages

Any other information that may be helpful

I've skipped all the frigate information since the software itself is not the issue here.

[inkeep-ai-assistant[bot]]

This issue has been reported by other users as well(1). The Hailo detector integration is designed to automatically detect your hardware architecture and select the appropriate default model(2).

In your Frigate configuration, both Hailo-8 and Hailo-8L use type: hailo8l in the detector configuration(2)(3). The configuration validator currently only accepts hailo8l as a valid type, even when using full Hailo-8 hardware(3).

When the Hailo detector downloads or uses a model, it should automatically select the correct model based on detected hardware(2)(1). However, there have been reports where models compiled for Hailo-8L are being used on Hailo-8 hardware, resulting in the warning "HEF was compiled for Hailo8L device, while the device itself is Hailo8"(1).

To resolve this:

1. Delete the cached model in /config/model_cache/hailo to force a redownload(1)
2. Ensure you're using the correct configuration with type: hailo8l in your detector settings(2)
3. The code should detect your Hailo-8 hardware and download the appropriate model automatically(2)

The inference time difference between a Hailo-8L model running on Hailo-8 hardware versus a properly compiled Hailo-8 model is typically only a few milliseconds (around 11ms vs 7-9ms)(1)(4).

For Frigate+ model compilation specifically, I don't have information in the available sources about the model compilation process or settings within the Frigate+ service itself. You may want to visit GitHub to report this as a Frigate+ service issue.

📚 Sources:

1. HEF was compiled for Hailo8L device, while the device itself is Hailo8.
2. Supported Hardware
3. [Bug]: [0.16.0‑beta1] Config validator rejects type: hailo8 (accepts only hailo8l)
4. Recommended hardware

---

Have another question? Just tag @inkeep.